To Stress test a SAN's storage you have to run against the LUNs presented and to ensure you saturate the SANs cache, and doing that - as I have done a few years back when I had such a chance to test the SAN infrastructure before going into production - will stress the SAN and will dramatically slow it down, causing problems for applications. If you don't do this, then the figures are useless in telling you at what load the IO subsystem can handle.

I also know it is possible to bring a SAN to its knees because on another gig I did, where I was brought in to help with a SQL Server performance issue for a well known high-volume internet sales site, the incumbent DBA had brought their systems down when he carried out a 'stress-test' using SQLIO without telling anyone he was doing the work.

Sorry, but no apology for my comments here.

Thanks anyway

Edit: I've added links here that are helpful to the points I raise...

http://technet.microsoft.com/en-us/library/cc966412.aspx

http://technet.microsoft.com/en-us/library/ms187104(v=sql.105).aspx

http://sqlblog.com/blogs/jonathan_kehayias/archive/2010/05/25/parsing-sqlio-output-to-excel-charts-using-regex-in-powershell.aspx

http://www.brentozar.com/archive/2008/09/finding-your-san-bottlenecks-with-sqlio/[/url]

http://blogs.technet.com/b/josebda/archive/2013/03/28/sqlio-powershell-and-storage-performance-measuring-iops-throughput-and-latency-for-both-local-disks-and-smb-file-shares.aspx

http://www.sqlteam.com/article/benchmarking-disk-io-performance-size-matters

http://blogs.technet.com/b/sqlpfeil/archive/2012/12/04/working-with-sqlio-and-analyzing-it-s-output.aspx

http://blogs.msdn.com/b/sqlmeditation/archive/2013/04/04/choosing-what-sqlio-tests-to-run-and-automating-sqlio-testing-somewhat.aspx

http://social.msdn.microsoft.com/Forums/sqlserver/en-US/a7ce8a90-22fc-456d-9f56-4956c42a78b0/sqlio-block-size-iossec